Novel classifier design for optimising the accuracy for identification of disturbance in power system
by B. Devi Vighneshwari; R. Neela
International Journal of Power Electronics (IJPELEC), Vol. 12, No. 2, 2020

Abstract: Origination of the disturbances in the power system is not a new problem and various technologies have evolved while various research-based contributions have addressed this problem to a large extent. Reviewing existing techniques shows much usage of iterative optimisation while designing the classifier. Hence, higher accuracy arrives at the cost of computational complexity in the existing system. Therefore, the proposed system introduces a novel framework where short-time Fourier transform is applied on the numerical-modelling on power signal generation corresponding to practical stages of various disturbances. A simple and novel feature extraction process is applied, which causes the system to enhance its potential for the classification process. Adopting IEEE 1159 standard, the disturbances of power system has been modelled, which is trained using dual-layer feedforward network. Comparative analysis shows proposed system outperforms conventional techniques by offering higher accuracy with lower computational complexity. From the analysis, it is observed that the proposed concept of detection offers higher accuracy of the classification within extremely very less iteration with less execution time of 2.6551 sec.

Online publication date: Wed, 05-Aug-2020

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Power Electronics (IJPELEC):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com